© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31943
    Prev
    Next
    INDEX
    Explanations

    first word in a phrase or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alic
    -0.13
     ‘
    -0.13
     Definitely
    -0.12
     emphas
    -0.12
     visibly
    -0.12
     ðĿ
    -0.12
     enrol
    -0.11
     https
    -0.11
     hadn
    -0.11
     LGBTQ
    -0.11
    POSITIVE LOGITS
     retarded
    0.16
     pimp
    0.15
     douche
    0.14
    ÃĤ
    0.14
     dudes
    0.14
     blogger
    0.13
     blogging
    0.13
     drunken
    0.13
     teh
    0.13
     crappy
    0.13
    Activations Density 1.226%

    No Known Activations